Coding-agent control plane with task scheduling and verified completion · Source
An orchestration loop for AI coding agents: the agent is the brain, flywheel is the control plane — it invokes the agent against a structured task, verifies completion claims with graders, and records the full execution history.
Flywheel by @johnayoungNot enough data yetzeroshot
17
Mindshare HN mentions, 90 days
Flywheel by @johnayoung0zeroshot
4
Adoption GitHub stars, not scored
Flywheel by @johnayoungNot yet verifiedzeroshot
2.2k
Release days last 90 days
Flywheel by @johnayoung
1zeroshot
41
Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only. After activation, the score is 80% mindshare plus 20% of the greater of mindshare and the vote score. GitHub stars do not affect the Index score. Mindshare uses a log scale; votes use the square-root curve and a 100-vote floor. Ranks use unrounded scores. Mindshare and adoption bars are log-scaled; the others are linear within this comparison. How the score is built
—Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only.
—Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only.